paper-with-me

홈 › Papers

Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards

2024-02-28 · Katherine Metcalf, Miguel Sarabia, Natalie Mackraz, Barry-John Theobald

Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that dynamics-aware reward functions improve the sample efficiency of PbRL by an order of magnitude. In our experiments we iterate between: (1) learning a dynamics-aware state-action representation (z^{sa}) via a self-supervised temporal consistency task, and (2) bootstrapping the preference-based reward function from (z^{sa}), which results in faster policy learning and better final policy performance. For example, on quadruped-walk, walker-walk, and cheetah-run, with 50 preference labels we achieve the same performance as existing approaches with 500 preference labels, and we recover 83\% and 66\% of ground truth reward policy performance versus only 38\% and 21\%. The performance gains demonstrate the benefits of explicitly learning a dynamics-aware reward model. Repo: \texttt{https://github.com/apple/ml-reed}.

📄 PDF Abstract BibTeX arXiv:2402.17975

Code (1)

apple/ml-reed 공식 구현 pytorch

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning

2026-04-15 · Qin Zhou, Guoyan Liang, Qianyi Yang, Jingyuan Chen 외 arxiv

Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness…

Reinforcement Learning

Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output

2026-06-09 · Guozheng Li, Xiyan Fu, Yiwen Guo arxiv

Current reinforcement learning from human feedback (RLHF) methods primarily rely on scalar rewards from a trained reward model (RM). While effective, scalar rewards are often noisy and fail to capture fine-grained prefer…

Reinforcement Learning

Dueling RL: Reinforcement Learning with Trajectory Preferences

2021-11-08 · Aldo Pacchiano, Aadirupa Saha, Jonathan Lee

We consider the problem of preference based reinforcement learning (PbRL), where, unlike traditional reinforcement learning, an agent receives feedback only in terms of a 1 bit (0/1) preference over a trajectory pair ins…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning

2025-06-14 · Sara Rajaram, R. James Cotton, Fabian H. Sinz arxiv

Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering. However, most previous PbRL work has not investigated th…

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards

2026-05-25 · Li Wang, Xiaodong Lu, Xiaohan Wang, Yikun Ban 외 arxiv

Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR intrinsically relies on ground-truth labe…

Reinforcement Learning